检索结果-内蒙古大学图书馆

international conference on Energy, Power and Environment: Towards Sustainable Growth (ICEPE)

作者： Abhishek Narwaria Arka Prokash Mazumdar Department of Computer Science & Engineering Malaviya National Institute of Technology Jaipur India

Forwarding Search Space (FSS) in position-based routing for Wireless sensor networks (WSN) controls unneces-sary transmissions, thereby balancing the sensor nodes' energy consumption. this research article aims to improve energy efficiency by considering the overlapping Forwarding Search Space (FSS) of two nodes simultaneously sending data to the base station. the article first introduces a mathematical model to represent the problem scenario. It then presents simulation results demonstrating the effectiveness of the proposed mecha-nism and other existing methods in reducing transmissions and balancing energy consumption among sensor nodes. the study considers metrics such as nodes in FSS, number of dead nodes, network lifetime, and number of messages for evaluating the performance of these methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Plant Recognition using Convolutional Neural Network 5

Plant Recognition using Convolutional Neural Network

引用

5th international conference on Computational Intelligence and Communication Technologies, CCICT 2022

作者： Pathak, Disha Mohini Srivastava, Somya Gupta, Shelly ABES Engineering College Computer Science Department 19th KM Stone NH 24 Uttar Pradesh Ghaziabad201009 India

ISBN: (数字)9781665472241

ISBN: (纸本)9781665472241

there are currently around 375000 known species of plants in the world. Expert botanists are able to easily classify and classify them based on either division/phylum, order, class, species, genus or family. But common people like students and new people in the field may find it difficult to classify them appropriately due to lack of experience or exposure to those plants. In the proposed solution, we plan on suggesting a system which would use deep learning models for image processing. this system can be trained on an ample amount of plant leaves images and tree images dataset containing pictures of various plant leaves and trees. Many prominent datasets like Flavia, Swedish Leaf datasets, etc can be used to train the model. the model will be built using a combination of 2-D Convolutional layers, Max Pooling and Dense layers. the system will take the images of the plant or tree as input and the built model will work on and predict the output. the output will be the classification of the plant. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

2022 IEEE 5th international conference on Automation, Electronics and Electrical Engineering, AUTEEE 2022

2022 IEEE 5th International Conference on Automation, Electr...

引用

5th IEEE international conference on Automation, Electronics and Electrical Engineering, AUTEEE 2022

ISBN: (纸本)9781665471978

the proceedings contain 209 papers. the topics discussed include: research on the fault diagnosis of pre-insertion resistor of AC filter circuit breakers;a new state estimation method for power cooling integrated energy system;longitudinal tracking control of autonomous vehicle based on improved model predictive control;energy dispatching strategy of remote islanded microgrid with energy storage vessel under emergency scenario;conventional detection methods for the combination of power lines and power towers;double-layer planning configuration with distributed PV power and energy storage system;evaluation method for insulation state of cable intermediate joint based on variable weight and set pair analysis;investigation on bandwidth enhancement in copper—carbon nanotube composite interconnects;research on human posture recognition system based on inertial sensor;research on driving technology of high-power motor for lunar soil drilling;coordinated planning model of charging station and rural multi-energy system considering traffic characteristics;optimal operation strategy of multi-energy microgrid considering orderly energy consumption;research on voltage and reactive power control strategy based on intelligent detection of abnormal data and coordinated control of dynamic reactive power;based on the wavelet transform and the half-wave Fourier transform study of intelligent decoupler algorithms;study of defense methods for additional generative adversarial networks;and an analytical model for frequency nadir prediction based on probabilistic production simulation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multimedia Privacy, Security, and Protection within the Blockchain: A Review 5

Multimedia Privacy, Security, and Protection within the Bloc...

引用

5th international conference on Contemporary Computing and Informatics, IC3I 2022

作者： thang, Pham Chien Trang, Ta thi Nguyet Tai, Bui Trong Prasanth, A. Thai Nguyen University of Sciences Thai Nguyen Viet Nam Thai Nguyen University International School Thai Nguyen Viet Nam Sri Venkateswara College of Engineering Department of Electronics and Communication Engineering Sriperumbudur India

ISBN: (纸本)9798350398267

the fact that wireless and wired sensor and actuator networks have different levels of security is a big challenge when it comes to allowing multimedia applications in the internet of things (IoT). In this work, we create a brand-new, effective security architecture that is both blockchain-based and multimedia-based to support diverse multimedia applications in the IoT. there are several challenges when transferring a file including multimedia data across wireless Internet of things network peers. their centralized structure, which increases the risk of security and reachability of users, is one of the key issues. One approach might be simply converting the system to a decentralised network by storing these data on the blockchain network. But it could compromise privacy, longer response time, low latency, and scalability concerns to address users' low reachability and security problems. Most audiovisual content shared in open spaces (such as wireless networks) runs the danger of being unlawfully duplicated and disseminated with little to no effort, which might have substantial repercussions, including privacy violations and brand damage. It is crucial that an IoT system appropriately secures and protects users' multimedia data and right to privacy. Unauthorized access to internet of things devices or applications is just one of the unfavorable outcomes of a breach in multimedia data security. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

sensor Placement Based on Cellular Communication Systems

Sensor Placement Based on Cellular Communication Systems

引用

Power Electronics, Computer Applications (ICPECA), IEEE international conference on

作者： Shaobo Yuan Jiaxu Chen Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (数字)9798331533694

ISBN: (纸本)9798331533700

this paper presents a novel approach for optimizing sensor placement within a designated area, leveraging a combination of cellular communication systems and feed-forward neural networks to streamline the selection process for operators. Initially, a modified hill-climbing algorithm, a form of local search, is implemented to generate preliminary data for sensor positioning. However, to prevent the algorithm from converging on local optima, a simulated annealing algorithm is subsequently employed to validate and refine the results. During the construction phase of the cellular communication system, flaws were detected in the evaluation metrics when using Modal Assurance Criterion (MAC) and singular value ratios, which led to the adoption of a feed-forward neural network. this neural network is utilized for both further optimization and a more accurate assessment of the sensor distribution. the study highlights the seamless integration of cellular communication systems with local search methods and underscores the significant improvements in optimization achieved through the use of neural networks. Ultimately, the research successfully develops a method for determining the optimal sensor positions, providing a robust solution for the effective deployment of cellular sensors in complex environments.

关键词： Measurement sensor placement Search methods Clustering algorithms Simulated annealing Computer applications Mobile communication Power electronics Feedforward neural networks Optimization

来源：评论

学校读者我要写书评

暂无评论

Single Node Acceleration of Generative Adversarial networks using HPC for Image Analytics 5

Single Node Acceleration of Generative Adversarial Networks ...

引用

5th international conference on Computational Intelligence and Intelligent Systems, CIIS 2022

作者： Ravikumar, Aswathy Sriraman, Harini School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India

ISBN: (纸本)9781450397612

Generative Adversarial networks (GAN) are approaches that are utilized for data augmentation, which facilitates the development of more accurate detection models for unusual or unbalanced datasets. Computer-assisted diagnostic methods may be made more reliable by using synthetic pictures generated by GAN. Generative adversarial networks are challenging to train because too unpredictable training dynamics may occur throughout the learning process, such as model collapse and vanishing gradients. For accurate and faster results the GAN network need to trained in parallel and distributed manner. We enhance the speed and precision of the Deep Convolutional Generative Adversarial networks (DCGAN) architecture by using its parallelism and executing it on High-Performance Computing platforms. the effective analysis of a DCGAN in Graphic processing Unit and Tensor processing Unit platforms in which each layer execution pattern is analyzed. the bottleneck is identified for the GAN structure for each execution platforms. the Central processing Unit is capable of processing neural network models, but it requires a great deal of time to do it. Graphic processing Unit in contrast, side, are a hundred times quicker than CPUs for Neural networks, however, they are prohibitively expensive compared to CPUs. Using the systolic array structure, TPU performs well on neural networks with high batch sizes but in GAN the shift between CPU and TPU is huge so it does not perform well. © 2022 ACM.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Neuromorphic analog circuits for robust on-chip always-on learning in spiking neural networks 5

Neuromorphic analog circuits for robust on-chip always-on le...

引用

5th IEEE international conference on Artificial Intelligence Circuits and Systems, AICAS 2023

作者： Rubino, Arianna Cartiglia, Matteo Payvand, Melika Indiveri, Giacomo University of Zurich Eth Zurich Institute of Neuroinformatics Switzerland

ISBN: (纸本)9798350332674

Mixed-signal neuromorphic systems represent a promising solution for solving extreme-edge computing tasks without relying on external computing resources. their spiking neural network circuits are optimized for processing sensory data on-line in continuous-time. However, their low precision and high variability can severely limit their performance. To address this issue and improve their robustness to inhomogeneities and noise in both their internal state variables and external input signals, we designed on-chip learning circuits with short-term analog dynamics and long-term tristate discretization mechanisms. An additional hysteretic stop-learning mechanism is included to improve stability and automatically disable weight updates when necessary, to enable continuous always-on learning. We designed a spiking neural network with these learning circuits in a prototype chip using a 180 nm CMOS technology. Simulation and silicon measurement results from the prototype chip are presented. these circuits enable the construction of large-scale spiking neural networks with online learning capabilities for real-world edge computing tasks. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Review on Secure Ad-Hoc networks for Wireless sensor Network 5th

Review on Secure Ad-Hoc Networks for Wireless Sensor Network

引用

5th international conference on Information and Communication Technology for Intelligent Systems, ICTIS 2021

作者： Chauhan, Kanika Yadav, Kalpana Singh, Ankita Indira Gandhi Delhi Technical University for Women New Delhi India

ISBN: (纸本)9789811641763

In a current scenario, wireless sensor networks (WSN) are the most common and trendy network technology which is used in wide areas of the real world. Recent results show that WSN has been used in many solicitation fields in the current world like many health organizations, supervision in the military, and many more. However, due to some cumbersome ideas of WSNs, protocols like Ad-hoc on-demand distance vector routing protocol (AODV) tend to cease malicious nodes and attacks. therefore, the attack is known as a playback attack. An isolated sensor node has a restricted number of transposition and estimation. As we know, sensor nodes have a restricted amount of vitality, so through this attack, we have a major influence on the network performance. While using memory-efficient data, structures called as bloom filters in this work make the functionality of the network better. © 2022, the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Towards long-distance inspection for in-pipe robots in water distribution systems with smart motion facilitated by particle filter and multi-phase motion controller

引用

INTELLIGENT SERVICE ROBOTICS 2022年第3期15卷 259-273页

作者： Kazeminasab, Saber Banks, M. Katherine Texas A&M Univ College Stn TX 77834 USA

Incidents in water distribution systems cause water loss and water contamination that requires the utility managers to assess the condition of pipelines frequently. However, pipelines are long and access to all parts of it is a challenging task;current in-pipe robots have the limitation of short-distance inspection and inability to operate in-service networks. In this work, we improve the design of our previously developed in-pipe robot as reported by Kazeminasab et al. (IEEE 5th international conference on robotics and automation engineering (ICRAE), 2020) and a multi-phase motion controller is proposed that ensures reliable motion for the robot during operation. the controller provides stabilized configuration with zero velocity at junctions (i.e. phase 1), stabilized configuration with velocity tracking at straight paths (i.e. phase 2), and facilitates desired amount of rotation around two axes for the robot (i.e. phase 3). We propose a localization technique with a particle filter that receives information about the surrounding environment with a rangefinder sensor. the map of the operation that is needed for the particle filter is an array that comprises non-straight paths in the operation that the robot passes through. We also develop a method that facilitates smart navigation for the robot in different configurations of pipelines. In this method, the localizer (i.e. particle filter) is synchronized with the multi-phase motion controller, and the robot switches between different phases of the controller based on its location in the network. We validated the functionality of the controller in the three phases with simulations and also the localization and navigation methods with experimental results. the results show that the robot has smart navigation with the synchronized motion controller and the localizer inside pipelines.

关键词： In-pipe robots Water distribution networks Long-distance inspection Smart navigation

来源：评论

学校读者我要写书评

暂无评论

SLIM-Net: Rethinking how neural networks use systolic arrays 5

SLIM-Net: Rethinking how neural networks use systolic arrays

引用

5th IEEE international conference on Artificial Intelligence Circuits and Systems, AICAS 2023

作者： Dalgaty, thomas Lepecq, Maria Univ. Grenoble-Alpes CEA List GrenobleF-38000 France Univ. Paris-Saclay CEA List Gif-sur-YvetteF-91000 France

ISBN: (纸本)9798350332674

Systolic arrays of processing elements are widely used to massively parallelise neural network layers. However, the execution of traditional convolutional and fully-connected layers on such hardware typically requires a non-negligible latency to distribute data over the array before each operation - data is not immediately in-place. this arises from the fundamental incompatibility between the physical spatial nature of a systolic array and the un-physical form of existing neural networks. We propose the systolic lateral mixer network (SLIM-Net) in an effort to reconcile this mismatch. the architecture of SLIM-Net maps directly onto the physical structure of a systolic array such that, after evaluating one layer, data immediately finds itself where it needs to be to begin the next. To evaluate the potential of SLIM-Net we compare it to a UNet model on a COCO segmentation task and find that, for models of equivalent size, SLIM-Net not only achieves a slightly better performance but requires almost an order of magnitude fewer MAC operations. Furthermore, we implement a lateral mixing layer on a systolic smart imager chip which executes seven times faster than similar convolutional layers on the same hardware and provides encouraging initial insights into the practicality of this new neuromorphic approach. © 2023 IEEE.

关键词： Systolic arrays

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：